Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2018-03-01

AUTHORS

Kuntal Dey , Ritvik Shrivastava , Saroj Kaushik

ABSTRACT

The topical stance detection problem addresses detecting the stance of the text content with respect to a given topic: whether the sentiment of the given text content is in favor of (positive), is against (negative), or is none (neutral) towards the given topic. Using the concept of attention, we develop a two-phase solution. In the first phase, we classify subjectivity - whether a given tweet is neutral or subjective with respect to the given topic. In the second phase, we classify sentiment of the subjective tweets (ignoring the neutral tweets) - whether a given subjective tweet has a favor or against stance towards the topic. We propose a Long Short-Term memory (LSTM) based deep neural network for each phase, and embed attention at each of the phases. On the SemEval 2016 stance detection Twitter task dataset [7], we obtain a best-case macro F-score of 68.84% and a best-case accuracy of 60.2%, outperforming the existing deep learning based solutions. Our framework, T-PAN, is the first in the topical stance detection literature, that uses deep learning within a two-phase architecture. More... »

PAGES

529-536

Book

TITLE

Advances in Information Retrieval

ISBN

978-3-319-76940-0
978-3-319-76941-7

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-76941-7_40

DOI

http://dx.doi.org/10.1007/978-3-319-76941-7_40

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1101242748


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/17", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology and Cognitive Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "IBM Research - India", 
          "id": "https://www.grid.ac/institutes/grid.481550.d", 
          "name": [
            "IBM Research, New Delhi, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Dey", 
        "givenName": "Kuntal", 
        "id": "sg:person.012701231562.41", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012701231562.41"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "NSIT, New Delhi, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shrivastava", 
        "givenName": "Ritvik", 
        "id": "sg:person.012431733344.51", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012431733344.51"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Indian Institute of Technology Delhi", 
          "id": "https://www.grid.ac/institutes/grid.417967.a", 
          "name": [
            "IIT Delhi, New Delhi, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kaushik", 
        "givenName": "Saroj", 
        "id": "sg:person.010245136346.59", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010245136346.59"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.24963/ijcai.2017/557", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1096024322"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/d16-1084", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098653303"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/s14-2009", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099138402"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3115/v1/s14-2009", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099138402"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s16-1062", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099151398"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s16-1064", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099151400"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s16-1067", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099151403"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s16-1069", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099151405"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s16-1070", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099151406"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s16-1073", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099151409"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s16-1074", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099151410"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s16-1075", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099151411"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-03-01", 
    "datePublishedReg": "2018-03-01", 
    "description": "The topical stance detection problem addresses detecting the stance of the text content with respect to a given topic: whether the sentiment of the given text content is in favor of (positive), is against (negative), or is none (neutral) towards the given topic. Using the concept of attention, we develop a two-phase solution. In the first phase, we classify subjectivity - whether a given tweet is neutral or subjective with respect to the given topic. In the second phase, we classify sentiment of the subjective tweets (ignoring the neutral tweets) - whether a given subjective tweet has a favor or against stance towards the topic. We propose a Long Short-Term memory (LSTM) based deep neural network for each phase, and embed attention at each of the phases. On the SemEval 2016 stance detection Twitter task dataset [7], we obtain a best-case macro F-score of 68.84% and a best-case accuracy of 60.2%, outperforming the existing deep learning based solutions. Our framework, T-PAN, is the first in the topical stance detection literature, that uses deep learning within a two-phase architecture.", 
    "editor": [
      {
        "familyName": "Pasi", 
        "givenName": "Gabriella", 
        "type": "Person"
      }, 
      {
        "familyName": "Piwowarski", 
        "givenName": "Benjamin", 
        "type": "Person"
      }, 
      {
        "familyName": "Azzopardi", 
        "givenName": "Leif", 
        "type": "Person"
      }, 
      {
        "familyName": "Hanbury", 
        "givenName": "Allan", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-76941-7_40", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-76940-0", 
        "978-3-319-76941-7"
      ], 
      "name": "Advances in Information Retrieval", 
      "type": "Book"
    }, 
    "name": "Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention", 
    "pagination": "529-536", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-76941-7_40"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "066dac6fbed6c57d0a48a30bf47819d3605cf7d5d45e844a0d7283e30dea74e3"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1101242748"
        ]
      }
    ], 
    "publisher": {
      "location": "Cham", 
      "name": "Springer International Publishing", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-76941-7_40", 
      "https://app.dimensions.ai/details/publication/pub.1101242748"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T05:01", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000325_0000000325/records_100806_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-3-319-76941-7_40"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-76941-7_40'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-76941-7_40'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-76941-7_40'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-76941-7_40'


 

This table displays all metadata directly associated to this object as RDF triples.

132 TRIPLES      23 PREDICATES      37 URIs      19 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-76941-7_40 schema:about anzsrc-for:17
2 anzsrc-for:1701
3 schema:author N5dc6fb55e3684416aac6d98f4df709cb
4 schema:citation https://doi.org/10.18653/v1/d16-1084
5 https://doi.org/10.18653/v1/s16-1062
6 https://doi.org/10.18653/v1/s16-1064
7 https://doi.org/10.18653/v1/s16-1067
8 https://doi.org/10.18653/v1/s16-1069
9 https://doi.org/10.18653/v1/s16-1070
10 https://doi.org/10.18653/v1/s16-1073
11 https://doi.org/10.18653/v1/s16-1074
12 https://doi.org/10.18653/v1/s16-1075
13 https://doi.org/10.24963/ijcai.2017/557
14 https://doi.org/10.3115/v1/s14-2009
15 schema:datePublished 2018-03-01
16 schema:datePublishedReg 2018-03-01
17 schema:description The topical stance detection problem addresses detecting the stance of the text content with respect to a given topic: whether the sentiment of the given text content is in favor of (positive), is against (negative), or is none (neutral) towards the given topic. Using the concept of attention, we develop a two-phase solution. In the first phase, we classify subjectivity - whether a given tweet is neutral or subjective with respect to the given topic. In the second phase, we classify sentiment of the subjective tweets (ignoring the neutral tweets) - whether a given subjective tweet has a favor or against stance towards the topic. We propose a Long Short-Term memory (LSTM) based deep neural network for each phase, and embed attention at each of the phases. On the SemEval 2016 stance detection Twitter task dataset [7], we obtain a best-case macro F-score of 68.84% and a best-case accuracy of 60.2%, outperforming the existing deep learning based solutions. Our framework, T-PAN, is the first in the topical stance detection literature, that uses deep learning within a two-phase architecture.
18 schema:editor N6de1eaa2f55e475984bd7bfe7e2bed59
19 schema:genre chapter
20 schema:inLanguage en
21 schema:isAccessibleForFree true
22 schema:isPartOf N66c6371a899f43b5bf44ff3b8146798f
23 schema:name Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention
24 schema:pagination 529-536
25 schema:productId N38f72604cdb04f8a908a9dcfbfb56a8f
26 N8874686b7565409ebb1c9da26700c2aa
27 Nb8fd1c69ed2041eaa06bdfa82d990284
28 schema:publisher N98eb116ef5f34fa7ab4b555b9c53b000
29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101242748
30 https://doi.org/10.1007/978-3-319-76941-7_40
31 schema:sdDatePublished 2019-04-16T05:01
32 schema:sdLicense https://scigraph.springernature.com/explorer/license/
33 schema:sdPublisher N4c3003ef7b234af89253fb4961f951cc
34 schema:url https://link.springer.com/10.1007%2F978-3-319-76941-7_40
35 sgo:license sg:explorer/license/
36 sgo:sdDataset chapters
37 rdf:type schema:Chapter
38 N27f79c6ec3004eb990f5e04cdac90360 schema:name NSIT, New Delhi, India
39 rdf:type schema:Organization
40 N38f72604cdb04f8a908a9dcfbfb56a8f schema:name readcube_id
41 schema:value 066dac6fbed6c57d0a48a30bf47819d3605cf7d5d45e844a0d7283e30dea74e3
42 rdf:type schema:PropertyValue
43 N4c3003ef7b234af89253fb4961f951cc schema:name Springer Nature - SN SciGraph project
44 rdf:type schema:Organization
45 N574c00a1021446929a9442bb7dde2f93 rdf:first N5c20f403743e49b2951a0ccb7ee36155
46 rdf:rest rdf:nil
47 N5c20f403743e49b2951a0ccb7ee36155 schema:familyName Hanbury
48 schema:givenName Allan
49 rdf:type schema:Person
50 N5dc6fb55e3684416aac6d98f4df709cb rdf:first sg:person.012701231562.41
51 rdf:rest Nf0b357d120dd4035aa702359114012e5
52 N60398ada04664d9981133c3392fbfebb rdf:first Nafbf541c139044bcbf970bdbd4368c02
53 rdf:rest N574c00a1021446929a9442bb7dde2f93
54 N66c6371a899f43b5bf44ff3b8146798f schema:isbn 978-3-319-76940-0
55 978-3-319-76941-7
56 schema:name Advances in Information Retrieval
57 rdf:type schema:Book
58 N6abe345e5ec5448d95e228bc26a33054 rdf:first sg:person.010245136346.59
59 rdf:rest rdf:nil
60 N6de1eaa2f55e475984bd7bfe7e2bed59 rdf:first N93fff9c460b141f1b802220d92ecbb09
61 rdf:rest Ne9bb3cb43ed64fb6a2b188550a806fca
62 N8874686b7565409ebb1c9da26700c2aa schema:name dimensions_id
63 schema:value pub.1101242748
64 rdf:type schema:PropertyValue
65 N93fff9c460b141f1b802220d92ecbb09 schema:familyName Pasi
66 schema:givenName Gabriella
67 rdf:type schema:Person
68 N98eb116ef5f34fa7ab4b555b9c53b000 schema:location Cham
69 schema:name Springer International Publishing
70 rdf:type schema:Organisation
71 Na6a39a6aee3e419aa1857b6647ec9fb5 schema:familyName Piwowarski
72 schema:givenName Benjamin
73 rdf:type schema:Person
74 Nafbf541c139044bcbf970bdbd4368c02 schema:familyName Azzopardi
75 schema:givenName Leif
76 rdf:type schema:Person
77 Nb8fd1c69ed2041eaa06bdfa82d990284 schema:name doi
78 schema:value 10.1007/978-3-319-76941-7_40
79 rdf:type schema:PropertyValue
80 Ne9bb3cb43ed64fb6a2b188550a806fca rdf:first Na6a39a6aee3e419aa1857b6647ec9fb5
81 rdf:rest N60398ada04664d9981133c3392fbfebb
82 Nf0b357d120dd4035aa702359114012e5 rdf:first sg:person.012431733344.51
83 rdf:rest N6abe345e5ec5448d95e228bc26a33054
84 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
85 schema:name Psychology and Cognitive Sciences
86 rdf:type schema:DefinedTerm
87 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
88 schema:name Psychology
89 rdf:type schema:DefinedTerm
90 sg:person.010245136346.59 schema:affiliation https://www.grid.ac/institutes/grid.417967.a
91 schema:familyName Kaushik
92 schema:givenName Saroj
93 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010245136346.59
94 rdf:type schema:Person
95 sg:person.012431733344.51 schema:affiliation N27f79c6ec3004eb990f5e04cdac90360
96 schema:familyName Shrivastava
97 schema:givenName Ritvik
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012431733344.51
99 rdf:type schema:Person
100 sg:person.012701231562.41 schema:affiliation https://www.grid.ac/institutes/grid.481550.d
101 schema:familyName Dey
102 schema:givenName Kuntal
103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012701231562.41
104 rdf:type schema:Person
105 https://doi.org/10.18653/v1/d16-1084 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098653303
106 rdf:type schema:CreativeWork
107 https://doi.org/10.18653/v1/s16-1062 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099151398
108 rdf:type schema:CreativeWork
109 https://doi.org/10.18653/v1/s16-1064 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099151400
110 rdf:type schema:CreativeWork
111 https://doi.org/10.18653/v1/s16-1067 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099151403
112 rdf:type schema:CreativeWork
113 https://doi.org/10.18653/v1/s16-1069 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099151405
114 rdf:type schema:CreativeWork
115 https://doi.org/10.18653/v1/s16-1070 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099151406
116 rdf:type schema:CreativeWork
117 https://doi.org/10.18653/v1/s16-1073 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099151409
118 rdf:type schema:CreativeWork
119 https://doi.org/10.18653/v1/s16-1074 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099151410
120 rdf:type schema:CreativeWork
121 https://doi.org/10.18653/v1/s16-1075 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099151411
122 rdf:type schema:CreativeWork
123 https://doi.org/10.24963/ijcai.2017/557 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096024322
124 rdf:type schema:CreativeWork
125 https://doi.org/10.3115/v1/s14-2009 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099138402
126 rdf:type schema:CreativeWork
127 https://www.grid.ac/institutes/grid.417967.a schema:alternateName Indian Institute of Technology Delhi
128 schema:name IIT Delhi, New Delhi, India
129 rdf:type schema:Organization
130 https://www.grid.ac/institutes/grid.481550.d schema:alternateName IBM Research - India
131 schema:name IBM Research, New Delhi, India
132 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...